Original Contribution: The gamma model-A new neural model for temporal processing

By B. D. Vries, J. Príncipe. 1992

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Lifelong learning of human actions with deep neural network self-organization (2017, methodology): “This is due to an increase inmemory depth and temporal resolution following the idea of a Gammamemorymodel (de Vries & Príncipe, 1992).”
Neural net architectures for temporal sequence processing (2007, methodology): “As with the exponential trace kernel, the convolution of the gamma kernel with the input sequence can be computed incrementally (de Vries & Principe, 1991, 1992) .”
Nonlinear Time Series Analysis by Using Gamma Growing Neural Gas (2012, methodology): “In our previous work we have added Gamma filters [9] to SOM, NG and GNG, yielding the γ-SOM [10], γ-NG [11], and γ-GNG models [12], respectively.”
On-line learning algorithms for locally recurrent neural networks (1999, methodology): “[32], [33], for which the delay operator, used in conventional TDL’s, is replaced by a single pole discrete time filter.”
Global Synchronization in an Array of Delayed Neural Networks With Hybrid Coupling (2008, background): “It has been observed that an NN usually has a spatial nature due to the presence of a number of parallel pathways of a variety of axon sizes and lengths [31].”
Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system (1995, methodology): “GAMMA: In this approach, the speaker-dependent input vectors are mapped to the SI system (as in the LIN technique) using a gamma lter [8].”
Handbook of Neural Network Signal Processing (2000, background): “This is also implicitly done for (one hidden layer) neural networks, radial basis networks [10, 47, 74, 81], or boosting algorithms [37] where the input data are mapped to some representation given by the hidden layer, the RBF bumps, or the hypotheses space, respectively.”
Gamma-Filter Self-Organizing Neural Networks for Time Series Analysis (2011, methodology): “The Gamma filter [ 12 ,15] is defined in the time domain as”
Lifelong Learning of Action Representations with Deep Neural Self-Organization (2017, methodology): “We introduce a temporal GWR network that equips each neuron with an arbitrary number of context descriptor (Strickert and Hammer 2005) to increase the memory depth and temporal resolution in the spirit of a Gamma memory model (de Vries and Prı́ncipe 1992).”